CN109325671B - Space-time crowdsourcing online task allocation method and system - Google Patents

Space-time crowdsourcing online task allocation method and system Download PDF

Info

Publication number
CN109325671B
CN109325671B CN201811032833.0A CN201811032833A CN109325671B CN 109325671 B CN109325671 B CN 109325671B CN 201811032833 A CN201811032833 A CN 201811032833A CN 109325671 B CN109325671 B CN 109325671B
Authority
CN
China
Prior art keywords
task
path
tasks
crowdsourcing
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN201811032833.0A
Other languages
Chinese (zh)
Other versions
CN109325671A (en
Inventor
余敦辉
张笑笑
张灵莉
王意
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hubei University
Original Assignee
Hubei University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hubei University filed Critical Hubei University
Priority to CN201811032833.0A priority Critical patent/CN109325671B/en
Publication of CN109325671A publication Critical patent/CN109325671A/en
Application granted granted Critical
Publication of CN109325671B publication Critical patent/CN109325671B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Compared with the prior art, the method comprises the steps of screening a plurality of tasks to be allocated which meet the preset distance requirement as target tasks according to the first path of crowdsourcing workers carrying the tasks and the positions of the tasks to be allocated. And then, obtaining a plurality of route coincidence rates according to the first path of crowdsourcing workers who carry tasks and the route information of the screened target tasks. And finally, according to the route information of the target tasks and the route coincidence rate information, obtaining a plurality of corresponding profit growth values of workers, and distributing the target task with the largest profit growth value to crowdsourcing workers who carry the tasks, so that efficient multitask distribution is achieved, and meanwhile, the profitability of the platform, the merchants and the crowdsourcing workers is improved.

Description

Space-time crowdsourcing online task allocation method and system
Technical Field
The invention relates to the technical field of information, in particular to a space-time crowdsourcing online task allocation method and system.
Background
With the advent of the mobile internet era, a new model for solving problems through the intelligence and collaboration of the public, crowdsourcing, has emerged, essentially "crowdsourcing" is a combination of "public" and "outsourcing". In recent years, with the application and development of crowdsourcing technology, more extensive demands are brought, and space-time crowdsourcing (also referred to as space crowdsourcing or mobile crowdsourcing) is gradually formed and applied to various real-time vehicle-driving applications and takeout distribution platforms, such as dribble travel, Uber, state exclusive cars, fairy takeout and the like.
The space-time crowdsourcing refers to a novel crowdsourcing mode which distributes crowdsourcing tasks with space-time characteristics, issued by crowdsourcing task initiators, to unspecified crowdsourcing workers, requires the crowdsourcing workers to complete the crowdsourcing tasks and meet space-time constraint conditions specified by the tasks to obtain certain rewards.
However, the existing crowdsourcing task allocation mode is based on static scenes to allocate tasks, and crowdsourcing workers are irregularly and dynamically arranged one after another, so that the task allocation mode based on the static scenes cannot efficiently allocate multiple tasks to the crowdsourcing workers, the idle rate of the crowdsourcing workers is too high, and the technical problem of low crowdsourcing task processing efficiency exists.
Disclosure of Invention
In view of the above, embodiments of the present invention provide a method and system for space-time crowdsourcing online task allocation to improve efficiency and rationality of multitask allocation.
The embodiment of the invention is realized by the following steps:
a space-time crowdsourcing online task allocation method is characterized by comprising the following steps: screening a plurality of tasks to be distributed which meet the preset distance requirement as target tasks according to a first path of crowdsourcing workers who carry the tasks and the positions of the plurality of tasks to be distributed; the first path is a path between the current position of the crowdsourcing worker and the end position of the task carried by the crowdsourcing worker, and each task to be distributed has corresponding route information; according to the first path and the route information of each target task, obtaining the route coincidence rate of each target task; the route coincidence rate represents the coincidence degree of the first path and the route information on direction and distance; obtaining an expected income increase value of each target task according to the route information and the route coincidence rate of each target task; the expected revenue growth value characterizes a relative magnitude of revenue obtained after the target task is completed by the crowdsourcing worker; assigning the target task with the largest expected revenue growth value to the crowdsourcing worker.
Preferably, the step of screening out a plurality of tasks to be allocated, which meet the preset distance requirement, as target tasks according to the first path of crowdsourcing workers who have carried the tasks and the positions of the plurality of tasks to be allocated includes: respectively obtaining a second path of each task to be distributed according to the first path and the positions of the tasks to be distributed; the first path length corresponds to a first distance value, the second path is a path between the current position of the crowdsourcing worker and the position of the task to be distributed, and the second path length corresponds to a second distance value; respectively obtaining the crowdsourcing task loss ratio of each task to be distributed according to the ratio of the first distance value to the second distance value corresponding to each task to be distributed; and respectively comparing the crowdsourcing task loss ratio of each task to be distributed with a preset loss threshold, and taking the task to be distributed with the crowdsourcing task loss ratio smaller than the loss threshold as the target task.
Preferably, the step of obtaining a route coincidence rate of each target task according to the first path and the route information of each target task includes: respectively obtaining a third distance of each target task according to the first path and the position of each target task, wherein the third distance is the shortest distance between the position of the target task and the first path; respectively obtaining direction information of each target task according to the all-time path and the first path of each target task, wherein the direction information represents the direction relationship between the all-time path and the first path of each target task; the path-all-time characterizes a travel route when the target task is completed individually; and distributing weights to the direction information and the third distance and calculating to obtain the route coincidence rate of each target task.
Preferably, after the obtaining of the route coincidence rate of each target task and before the obtaining of the expected profit growth value of each target task according to the route information and the route coincidence rate of each target task, the method further includes: determining at least one target task meeting a preset route coincidence rate range from the plurality of target tasks as a candidate task according to the size of the route coincidence rate; wherein the obtaining an expected revenue increase value of each target task according to the route information and the route coincidence rate of each target task comprises: obtaining an expected income increase value of each candidate task according to the route information and the route coincidence rate of each candidate task; wherein said assigning the target task with the largest expected revenue growth value to the crowdsourcing workers comprises: assigning the candidate task with the largest expected revenue growth value to the crowdsourcing worker.
Preferably, before the step of screening out a plurality of tasks to be assigned meeting the preset distance requirement as target tasks according to the first path of crowdsourcing workers who have carried the tasks and the positions of the plurality of tasks to be assigned, the method further includes: acquiring a first time difference corresponding to a published task and a second time difference generated by the crowd-sourcing worker moving from a current position to a position of the published task in a shortest path; and determining the published task with the first time difference larger than the second time difference as the task to be distributed.
Preferably, before the step of screening out a plurality of tasks to be assigned meeting the preset distance requirement as target tasks according to the first path of crowdsourcing workers who have carried the tasks and the positions of the plurality of tasks to be assigned, the method further includes: respectively defining a target area range for each published task of unallocated workers; according to the probability that the target area range is visited by random workers of each unassigned task, obtaining the position entropy of each issued task, wherein the position entropy represents the disorder of the visited tasks of the issued task by the random workers of the unassigned task; and sequentially distributing tasks for the random workers according to the position entropy of the issued tasks. .
Preferably, the step of sequentially assigning tasks to the random worker comprises: acquiring the travel expense between each random worker and the published task; matching the issued task with the minimum position entropy and the random worker with the minimum issued task travel expense; and after the matching is successful, the mobile terminal is taken as a crowdsourcing worker with a task.
Preferably, the trip cost is calculated using manhattan distance.
Preferably, a spatiotemporal crowdsourcing online task distribution system comprises: the task screening module is used for screening a plurality of tasks to be distributed which meet the preset distance requirement as target tasks according to a first path of crowdsourcing workers who carry the tasks and the positions of the tasks to be distributed; the first path is a path between the current position of the crowdsourcing worker and the end position of the task carried by the crowdsourcing worker, and each task to be distributed has corresponding route information; the route calculation module is used for obtaining the route coincidence rate of each target task according to the first path and the route information of each target task; the route coincidence rate represents the coincidence degree of the first path and the route information on direction and distance; the profit calculation module is used for obtaining an expected profit growth value of each target task according to the route information of each target task and the route coincidence rate; the expected revenue growth value characterizes a relative magnitude of revenue obtained after the target task is completed by the crowdsourcing worker; an allocation module to allocate the target task with the largest expected revenue growth value to the crowdsourcing worker.
Preferably, the task screening module includes: the second path acquisition unit is used for respectively acquiring a second path of each task to be distributed according to the first path and the positions of the tasks to be distributed; the first path length corresponds to a first distance value, the second path is a path between the current position of the crowdsourcing worker and the position of the task to be distributed, and the second path length corresponds to a second distance value; a task loss ratio obtaining unit, configured to obtain a crowdsourcing task loss ratio of each to-be-allocated task according to a ratio of the first distance value to the second distance value corresponding to each to-be-allocated task; and the comparison unit is used for respectively comparing the crowdsourcing task loss ratio of each task to be distributed with a preset loss threshold value, and taking the task to be distributed with the crowdsourcing task loss ratio smaller than the loss threshold value as the target task.
Compared with the prior art, the space-time crowdsourcing online task allocation method and the space-time crowdsourcing online task allocation system have the following beneficial effects:
according to the task allocation method and device, the tasks to be allocated which meet the requirements are screened out through the first path of crowdsourcing workers who carry the tasks and the position relation of the tasks to be allocated, the tasks with unreasonable distances are eliminated, and the reasonability of the crowdsourcing workers in obtaining the task distances can be guaranteed. And then calculating the route information of each target task and the first path which is traveled by the crowdsourcing worker to obtain a route coincidence rate, wherein the higher the route coincidence degree is, the more suitable the crowdsourcing worker can be represented by the task to be distributed, and the more matched target task can be screened out. Under the condition of route matching, after the route information of different target tasks is clarified, the relative size of earnings obtained by crowdsourcing workers for picking up the tasks and completing the tasks is checked, and finally the earnings growth value of the crowdsourcing workers is obtained, so that the most matched target task for the crowdsourcing workers is measured. The process of screening the target task which is finally distributed from the tasks to be distributed can be constantly calculated according to the real-time first path in the moving process of crowdsourcing workers, so that the timeliness of the crowdsourcing worker states is guaranteed, the dynamic multi-task efficient task distribution effect is achieved, the processing efficiency of crowdsourcing tasks is improved, and the idling rate of crowdsourcing workers is reduced due to the dynamic distribution of the tasks.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic diagram illustrating interaction between a server and a local terminal according to a preferred embodiment of the present invention.
Fig. 2 is a flowchart of a space-time crowdsourcing online task allocation method according to a first embodiment of the present invention.
Fig. 3 is a flowchart illustrating a specific step of step S11 in fig. 2.
Fig. 4 is a flowchart illustrating a specific step of step S12 in fig. 2.
FIG. 5 is a flowchart of a spatiotemporal crowdsourcing online task allocation method according to a second embodiment of the invention.
FIG. 6 is a flowchart of a spatiotemporal crowdsourcing online task allocation method according to a third embodiment of the invention.
Fig. 7 is a schematic diagram of the task and crowd-sourcing worker location of an embodiment of a space-time crowd-sourcing online task allocation method according to a preferred embodiment of the present invention.
Fig. 8 is a task route diagram of an embodiment of a space-time crowdsourcing online task allocation method according to a preferred embodiment of the invention.
FIG. 9 is a functional block diagram of a spatiotemporal crowdsourcing online task distribution system according to a fourth embodiment of the invention.
Icon: 100-a server; 201-local terminal; 202-local terminal; 300-space-time crowdsourcing online task distribution system; 301-task screening module; 302-route calculation module; 303-revenue calculation module; 304-allocation module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Fig. 1 is a schematic diagram illustrating the interaction of the server 100 with the local terminal 201 and the local terminal 202 according to the preferred embodiment of the present invention. The server 100 is communicatively connected to one or more local terminals via a network for data communication or interaction. The server 100 may be a web server, a database server, or the like. The local terminal may be a Personal Computer (PC), a tablet PC, a smart phone, a Personal Digital Assistant (PDA), or the like. Each crowdsourcing worker and task initiator (merchant or user) may have a local terminal 201 for communication and data connection with the server 100 at work.
The server 100 may be a platform of the present invention, and when a business or a demander issues a task, the server 100 may be connected to issue the task.
It should be noted that, in the present invention, the information of crowd-sourced workers and random workers may be represented by network devices or mobile devices carried by the workers and connectable to the server 100.
First embodiment
Referring to fig. 2, a flowchart of a spatiotemporal crowdsourcing online task allocation method applied to the server (the overall hardware device of the invention) shown in fig. 1 according to a preferred embodiment of the invention is shown. The specific process shown in fig. 2 will be described in detail below.
Step S11: and screening a plurality of tasks to be distributed which meet the preset requirements as target tasks.
Specifically, in the step, a plurality of tasks to be allocated which meet the preset distance requirement can be screened out as target tasks according to the first path of crowdsourcing workers who carry the tasks and the positions of the plurality of tasks to be allocated; the first path is a path between the current position of the crowdsourcing worker and the end position of the task carried by the crowdsourcing worker, and each task to be distributed has corresponding route information. The tasks to be distributed can be preliminarily screened by the step, the phenomenon that the distance between the initial position of the tasks and the position of crowdsourcing workers is too far is avoided, and the task distribution rationality is improved.
The carried task means that the user or the business is already picked up by crowdsourcing workers after the task is issued, and the crowdsourcing workers are in the process of completing the carried task. The task to be allocated means that no crowdsourcing worker takes the task after the task demand is issued by the merchant or the user. The task may be a transportation, communication, or other related task, such as delivery of take-out, delivery of a taxi, transportation of goods, or the like, without limitation.
The number of the carried tasks may be multiple.
The position information may be coordinates representing the position, or may represent a relative position between the position and a specific position, and is not limited.
As shown in fig. 3, further, the step may further include:
step S111: a second path is obtained.
In this step, specifically, a second path of each task to be allocated is obtained according to the first path and the positions of the plurality of tasks to be allocated; the first path length corresponds to a first distance value, the second path is a path between the current position of the crowdsourcing worker and the position of the task to be distributed, and the second path length corresponds to a second distance value. The second distance value may represent a distance that crowdsourcing workers pick up the task.
The first distance value and the second distance value can adopt Manhattan distance, and can also adopt other straight line distance or the line distance or custom distance to calculate.
Step S112: and acquiring a crowdsourcing task loss ratio.
And respectively obtaining the crowdsourcing task loss ratio of each task to be distributed according to the ratio of the first distance value to the second distance value corresponding to each task to be distributed. In this step, a ratio of the first distance value to the second distance value corresponding to each task to be allocated may be specifically expressed as a ratio of the second distance value to the first distance value, or may be a ratio of the first distance value to the second distance value, which is not limited. The length of the second distance value relative to the first distance value can be quantified through the step, and comparison is facilitated.
Step S113: and screening the tasks to be distributed which meet the preset requirements as target tasks.
And respectively comparing the crowdsourcing task loss ratio of each task to be distributed with a preset loss threshold, and taking the task to be distributed with the crowdsourcing task loss ratio smaller than the loss threshold as the target task.
If the second distance value adopted in step S112 is greater than the first distance value, a task loss ratio smaller than the loss threshold value should be selected during the comparison, and the corresponding task is a task to be allocated that meets the preset requirement.
Step S12: and calculating the route coincidence rate.
In this step, a route coincidence rate of each target task can be obtained according to the first path and the route information of each target task; the route coincidence rate represents the coincidence degree of the first path and the route information in direction and distance.
As shown in fig. 4, the specific step S12 further includes:
step S121: a third distance is obtained.
And respectively obtaining a third distance of each target task according to the first path and the position of each target task, wherein the third distance is the shortest distance between the position of the target task and the first path. Specifically, the distance from the position point set (position set of the first route) of the crowdsourcing worker to the line segment set of the task position to be assigned is calculated, and the shortest distance (third distance) between the position point set and the line segment set is calculated by combining the starting position, the ending position and the positions and the number of the path points of the first route.
The distance from the crowdsourcing worker to the position of the task to be distributed can be reduced to the minimum through the calculated third distance, namely the optimal path is reached, and detour is avoided.
Step S122: and acquiring the direction relation between the all-time path and the first path of the target task.
Specifically, according to the all-time path and the first path of each target task, direction information of each target task is respectively obtained, and the direction information represents the direction relationship between the all-time path and the first path of the target task; the path-all-time characterizes a travel route when the target task is completed individually.
The directional relationship may be a directional angular relationship of the overall route.
Step S123: and calculating the route coincidence rate.
Specifically, weights are distributed to the direction information and the third distance and calculated, and a route coincidence rate of each target task is obtained. The calculation of the coincidence rate of the paths through weight distribution can avoid the situation that the two task paths are in the same direction but far away from each other, or the two task paths are only close to each other at a certain position but have far-apart overall directions. The calculation mode can ensure that crowdsourcing workers can acquire more tasks to be distributed in the same route. The weight distribution size can be confirmed according to other parameters such as the number of tasks and the like, and can be adjusted according to the later use feedback information.
Step S13: a corresponding expected revenue growth value for the worker is obtained.
Obtaining an expected income increase value of each target task according to the route information and the route coincidence rate of each target task; the expected revenue growth value characterizes a relative magnitude of revenue obtained after the target task is completed by the crowdsourcing worker. The profit growth value represents the amount of profit obtained by crowdsourcing workers in an equivalent time period when facing different tasks (or the net income ratio obtained after completing the tasks, namely the profit rate is 1-driving cost), and the larger the profit growth value is, the better the profit is, and the better the crowdsourcing workers are.
Specifically, after obtaining the route coincidence rate of each target task, and before obtaining the expected profit growth value of each target task according to the route information and the route coincidence rate of each target task (before step S13), the method further includes:
and determining at least one target task meeting a preset route coincidence rate range from the plurality of target tasks as a candidate task according to the size of the route coincidence rate, filtering the tasks with low route coincidence rate, and adjusting the range of the route coincidence rate according to the market task amount, the task distance and the like.
Wherein the obtaining an expected revenue increase value of each target task according to the route information and the route coincidence rate of each target task comprises:
obtaining an expected income increase value of each candidate task according to the route information and the route coincidence rate of each candidate task; namely, the candidate persons are screened secondarily, so that the target task with high route coincidence rate is avoided, but the expected income value is relatively low for crowdsourcing workers.
Wherein said assigning the target task with the largest expected revenue growth value to the crowdsourcing workers comprises:
assigning the candidate task with the largest expected revenue growth value to the crowdsourcing worker. The method ensures that crowdsourcing workers can give consideration to the maximized income when completing tasks, and realizes win-win.
The calculation of the specific profit value may also take into account the travel costs of crowdsourcing workers in the idle state.
Step S14: and performing task allocation.
That is, the target task with the largest expected revenue growth value is assigned to the crowdsourcing worker.
When the method is additionally required to be explained, in the execution of the method steps, the task is forcibly distributed to avoid crowdsourcing workers; and the optimization is more humanized, the crowdsourcing workers can be reminded whether to accept the tasks during task allocation, the selection time is set, and when the crowdsourcing workers refuse to receive the tasks, the rejected target tasks are excluded during the next calculation and are not matched with the crowdsourcing workers.
Second embodiment
Referring to fig. 5, in this embodiment, different from the first embodiment, before the step of screening out a plurality of tasks to be assigned that meet preset requirements according to the first path of crowdsourcing workers who have carried the tasks and the position information of the tasks to be assigned (i.e., step S11), the method further includes:
step S101: and selecting a task to be distributed.
Acquiring a first time difference corresponding to a published task and a second time difference generated by the crowd-sourcing worker moving from a current position to a position of the published task in a shortest path; and determining the published task with the first time difference larger than the second time difference as the task to be distributed. .
The issued tasks represent the tasks issued by the user/merchant and the demander on the platform; the first time difference represents the time difference between the issuance of two tasks, and may be, for example, the difference between the issuance time of the newly issued task and the issuance time of the task carried by the crowd-sourced worker. The calculation and the restriction of the step can ensure that the task to be distributed is close enough to crowdsourcing workers, avoid the crowdsourcing workers from overtaking to a task position far away from the road, and ensure that the crowdsourcing workers can get the task before the waiting time of the task is over.
Third embodiment
As shown in fig. 6, in this embodiment, unlike the first embodiment, before the step of screening out a plurality of tasks to be assigned that meet preset requirements according to the first path of crowdsourcing workers who have carried the tasks and the position information of the tasks to be assigned (i.e., step S11), the method further includes:
step S21: a target area range is respectively defined for the published tasks of each unallocated worker. The area range can be a circular area, can be positioned and acquired and defined in the form of a GPS, a Beidou navigation system or a wireless base station, ensures reasonable distance during distribution, and can be defined according to urban roads, cell ranges and the like.
Step S22: and acquiring the position entropy of random workers.
According to the probability that the target area range is visited by random workers of each unassigned task, obtaining the position entropy of the random workers of each unassigned task, wherein the position entropy represents the disorder of the visited random workers of the distributed task; random workers, i.e. randomly moving workers who do not pick up tasks, determine the positions and the sections where a random worker often appears through probability statistics, and know the access relation between the random worker and the published tasks. The probability of the target area range being accessed can be calculated by counting historical data or defining data which is representative in a certain period, and updating the data regularly to ensure timeliness. Multiple random workers may be present within the target area of a task.
In addition, a position entropy threshold value can be set, tasks with excessively high position entropy are removed, and published tasks which do not exceed the threshold value are reserved. And the reasonability of the finally matched published task is ensured.
Step S23: and acquiring the travel expense between each random worker and the published task. The trip cost may be the manhattan distance between the random worker and the published task location or the distance traveled to pick up the task.
Step S24: matching the random worker of the unassigned task with the minimum position entropy with the task with the minimum travel overhead between the random worker and the random worker; and after the matching is successful, the mobile terminal is taken as a crowdsourcing worker with a task. In the process of completing the carried task, the crowdsourcing worker who carries the task can start to perform the multi-task continuous drawing calculation through step S11, so as to increase the income of the crowdsourcing worker.
Through the steps S23 and S24, the published tasks with the minimum position entropy can be screened out among the tasks, and the published tasks with low position entropy can enable the crowdsourcing workers to have higher route planning efficiency among the tasks relative to other workers, and routes and distances are more matched when other tasks are taken in the process of completing the tasks.
The above-mentioned travel overhead can be calculated using manhattan distance.
In order to make the above steps of the present invention easier to understand, the present invention is described by way of example with respect to the above embodiments, specifically as follows:
definition 1: crowdsourcing tasks
The space-time crowdsourcing task is defined as t ═ t<it,et,rt,pt,dt,ft>Wherein itAs a starting position of task t, etIs the end position of task t, rtRadius of extent, p, of task ttIs a taskService release time, dtAs task deadline, ftAnd the reward corresponding to the task t.
Definition 2: crowdsourcing workers
A spatiotemporal crowdsourcing worker refers to a person specifically performing a crowdsourcing task, defined as w ═ w<lw，aw，dw，rw，cw，sw>Wherein l iswIs the current position of worker w, awTime of arrival at the platform, dwTime to leave the platform, rwRadius of the range of the task that the worker w can accept, cwTask capacity of w, swIs the historical task success rate of w.
Definition 3: space-time crowdsourcing task publishers
The space-time crowdsourcing task publisher refers to an initiator of a crowdsourcing task, and attributes such as starting and ending point positions, publishing, deadline and the like of the task are set by the initiator, and are defined as r<lr,ar,dr,sr>Wherein l isrIs the location of the publisher r, arTime of entry of publisher into platform, drTime of departure of publisher from platform, srPaying for the itinerary of the publisher.
Definition 4: online task allocation problem in space-time crowdsourcing environment
In a spatio-temporal crowdsourcing platform, given a set of crowdsourcing tasks T, a set of crowdsourcing workers W, and a utility function U (T, W), the TSC-OTA problem aims to find an allocation a that maximizes the total utility of the task allocation, i.e., maxsum (a) ═ Σt∈T，w∈WU (t, w), which satisfies the following constraints:
(1) platform should be at crowdsourcing task deadline dtGiving out corresponding task distribution results before;
(2) once the task allocation is given, it cannot be changed;
(3) task t contained in task assignment A must be assigned lwAs a center of circle, rwIs within the radius of the zone.
Definition 5: crowdsourcing worker profitability (earnings growth information of crowdsourcing worker)
CrowdsourcingThe worker profitability is the net income rate obtained by crowdsourcing workers after completing a task and is defined as iw＝1-wc(wc∈(0,1]) Wherein w iscRepresenting the cost of crowd-sourced workers traveling in an idle state, we assume here for simplicity of problem and computation that the cost of all crowd-sourced workers is the same and constant.
For example: as shown in FIG. 8, there are 3 crowdsourcing workers w in the current area1(1,1)，w2(4,3)，w3(9,2) and 5 crowdsourcing tasks t1(1,3)，t2(4,2)，t3(4,4)，t4(8,1)，t5(10,3). Since all distances of the present invention are manhattan distances, one grid in the figure may represent one unit distance. For the sake of calculation, we represent the area range of the task by the size of a circle.
Let current task t1In the region R1Total number of accesses
Figure BDA0001790166590000152
Wherein w 11 visit, w 21 visit, w3Not accessed; task t2In the region R2Total number of accesses
Figure BDA0001790166590000153
Wherein w 12 visits, w2Visit 3 times, w 31 visit; task t3In the region R3Total number of accesses
Figure BDA0001790166590000154
Wherein w 11 visit, w2Visit 3 times, w 31 visit; task t4In the region R4Total number of accesses
Figure BDA0001790166590000155
Wherein w1Not accessed, w 21 visit, w3Visit 2 times; task t5In the region R5Total number of accesses
Figure BDA0001790166590000156
Wherein w 12 visits, w 21 visit, w 31 visit, the results shown in table 1 can be obtained:
table 1: probability of worker occurrence in each area
Figure BDA0001790166590000151
Figure BDA0001790166590000161
The calculation results show that:
Figure BDA0001790166590000162
Figure BDA0001790166590000163
Figure BDA0001790166590000164
Figure BDA0001790166590000165
Figure BDA0001790166590000166
(C is any constant and can be determined according to unit selection).
Position entropy at this time: e (R)1)＝E(R5)＜E(R3)＜E(R4)＜E(R2) If g is 2(g represents an allocation threshold value, namely the first 2 tasks are selected for allocation, and the value of the specific g can be determined according to the platform requirement, the number of workers, the number of tasks and the like), the task t is determined1And t5And taking the candidate task as a next step of calculation.
As can be seen from FIG. 8, d (t)1,w1)＝2,d(t1,w2)＝3,d(t1,w3) When the distance task t is equal to 81The nearest worker is w1Same principle as d (t)5,w1)＝10,d(t5,w2)＝5,d(t5,w3) When the distance task t is 25The nearest worker is w3Algorithm will crowd source worker w1And w3As candidate crowdsourcing workers.
For example: the location of task T, worker W in coordinates is shown in FIG. 8. Since all distances in this section are manhattan distances, a grid in the figure can represent a unit distance (in the foregoing, we assume that crowdsourcing workers are traveling at a constant speed, so a grid represents a unit time in this example, one unit time being ten minutes).
Let the information of the elements in the set T, W be shown in Table 2. Assuming that the dynamic threshold λ of the task loss ratio is 0.2, the number of route points per task is set to be the same, i.e., f is 3, for convenience of calculation.
TABLE 2 task and worker information sheet
Figure BDA0001790166590000171
Set at w in the current region1,t1,t2,t3,t4,t5，(w1,t1) Is the assignment completed according to the algorithm of step one and worker w1Has been according to t1Starts to run on the route of (1) when t2,t3,t4,t5After successive occurrences, we can perform task allocation calculations as follows:
(1) the task time difference (i.e. the selection of the task to be assigned) is calculated. Crowdsourcing worker w1Starting from 9:00 according to t1Start to run when w1When the vehicle is driven to (3,1), t5Occurs when D5(t,tnow)＝(pt5-pt1)-mintd(5,1)-10 < 0, due to t5Does not comply with the constraint of the task time difference, so t5The next calculation is not possible. When w is1When the vehicle is driven to (3.5,1), t4Occurs when D4(t,tnow)＝(pt4-pt1)-mintd(4,1)Cp-10 < 0, due to t4Does not comply with the constraint of the task time difference, so t4The next calculation is not possible. When w is1When the vehicle continues to travel to (4,1), t2And t3At the same time, when D2(t,tnow)＝(pt2-pt1)-mintd(2,1)＝0，D3(t,tnow)＝(pt3-pt1)-mint d(3,1)10 > 0, due to t2And t3And (4) meeting the constraint of the task time difference, and performing the next calculation.
(2) And calculating the task loss ratio. t is t1Has a stroke distance d (e)t1-it1)＝10，t2And t3And w1Is d (l) betweenw-it2)＝2，d(lw-it3) When the ratio is 1, the task loss ratio
Figure BDA0001790166590000172
Ratio of task losses
Figure BDA0001790166590000173
Since we assume λ 0.2, t2And t3Are not higher than the constraint of the task loss ratio, and the next calculation can be carried out.
(3) And calculating the route coincidence rate. For convenience of calculation, the number of route points of each task is set to be the same, i.e. f2＝f3＝3。t2And t3The same approach point is used. At this time, the distance from the set of points of the crowd-sourced worker's route to the set of line segments of the target task, i.e., the third distance, is calculated as:
Figure BDA0001790166590000181
Figure BDA0001790166590000182
since at this time w1When the vehicle has traveled to (4,1), t2And t3And w1The angles between the current traveling direction of the crowdsourcing worker and the route direction of the target task are 0 ° and 14 ° (the angle between the current traveling direction of the crowdsourcing worker and the route direction of the target task, specifically, the included angle between the straight line between the current position of the crowdsourcing worker and the end point of the performed task and the straight line at the start point of the target task), and if α is equal to 1, the route coincidence rate is:
Figure BDA0001790166590000183
by Rc2And Rc3Computing a knowable task t2And t3Is 0.0365, and assuming that C is 0.1, it can be obtained
Figure BDA0001790166590000184
Since there are only two alternative tasks at this time, t will be2And t3And taking the next calculation as a candidate task.
(4) The rate of revenue growth of crowdsourced workers is calculated (the expected revenue growth value is calculated). As can be seen, d (e)t3-st3)＝8，d a1+ 3-4, so d-4 + 8-12. Assuming that δ is 0.5, the task unit price of the target task is per 1.5,
Figure BDA0001790166590000185
can obtain Sr30.8 × 1.5 × 10 ═ 12. Suppose cost w of crowdsourcing workers traveling in idle statec0.5, the earning rate of crowdsourcing workers iw＝1-wc1-0.5, in which case I2＝0.8×1.5×(10+7)-1.5×0.5×5-1.5×10＝1.65＞0I3The expected yield increase can be found when 0.8 × 1.5 × (10+8) -1.5 × 0.5 × 4-1.5 × 10 ═ 3.6 > 0:
Figure BDA0001790166590000186
it is obvious that
Figure BDA0001790166590000187
The algorithm makes the allocation<t3,w1>Worker w1Is assigned to t3Updating the route and continuing to drive until a new task is issuedThe algorithm now performs the calculation.
Fourth embodiment
As shown in fig. 9, the functional module diagram of a spatiotemporal crowdsourcing online task distribution system 300 provided by the present invention is illustrated, and the system includes:
the task screening module 301 is configured to screen out a plurality of tasks to be allocated that meet preset requirements according to the first path of crowdsourcing workers who have carried the tasks and the position information of the tasks to be allocated.
Specifically, the task screening module 301 includes: the second path acquisition unit is used for acquiring a second path according to the first path and the position information of the task to be distributed; the length of the first path corresponds to a first distance value and the length of the second path corresponds to a second distance value. And the task loss ratio acquisition unit is used for acquiring a crowdsourcing task loss ratio according to the ratio of the first distance value to the second distance value. And the comparison unit is used for comparing the crowdsourcing task loss ratio with a preset loss threshold value and screening a plurality of tasks to be distributed which meet the preset requirement.
And the route calculation module 302 is configured to obtain multiple route coincidence rate information according to the first path of the crowdsourcing worker who has carried the task and the screened multiple route information of the tasks to be allocated, which meet the preset requirement.
And the profit calculation module 303 is configured to obtain a plurality of corresponding profit growth information of crowdsourcing workers who have carried the task according to the plurality of screened route information of the task to be allocated which meets the preset requirement and the plurality of route coincidence rate information.
The allocating module 304 selects the crowdsourcing worker carrying the task with the optimal income growing information corresponding to the task to be allocated.
In summary, the following steps: according to the space-time crowdsourcing online task allocation method and system, tasks to be allocated are screened for matching proper crowdsourcing workers, the reasonability of matching distances between the crowdsourcing workers and the tasks is guaranteed, then calculation is carried out according to the tasks meeting preliminary requirements, the tasks with the highest route coincidence rate or the tasks with higher route coincidence rate are screened out, a plurality of tasks allocated to the crowdsourcing workers are guaranteed to have approximately the same route, and task completion efficiency is improved; finally, according to the tasks with higher route coincidence rate and the tasks with reasonable task distance, calculating the income growth value of the tasks for crowdsourcing workers; and finally, the most profitable/best task is preferably distributed to crowdsourcing workers, each crowdsourcing worker which appears randomly can be distributed by adopting the method, the crowdsourcing workers are analyzed in real time in the distribution process, the timeliness of multi-task distribution and the profitability of the crowdsourcing workers are guaranteed, and the multi-win result of a platform, the crowdsourcing workers and a task publisher or demander is achieved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (7)

1. A space-time crowdsourcing online task allocation method is characterized by comprising the following steps:
screening a plurality of tasks to be distributed which meet the preset distance requirement as target tasks according to a first path of crowdsourcing workers who carry the tasks and the positions of the plurality of tasks to be distributed; the first path is a path between the current position of the crowdsourcing worker and the end position of the task carried by the crowdsourcing worker, and each task to be distributed has corresponding route information;
the step of screening out a plurality of tasks to be allocated which meet the preset distance requirement as target tasks according to the first path of crowdsourcing workers who have carried the tasks and the positions of the plurality of tasks to be allocated comprises the following steps:
respectively obtaining a second path of each task to be distributed according to the first path and the positions of the tasks to be distributed; the first path length corresponds to a first distance value, the second path is a path between the current position of the crowdsourcing worker and the position of the task to be distributed, and the second path length corresponds to a second distance value; respectively obtaining the crowdsourcing task loss ratio of each task to be distributed according to the ratio of the first distance value to the second distance value corresponding to each task to be distributed; respectively comparing the crowdsourcing task loss ratio of each task to be allocated with a preset loss threshold, and taking the task to be allocated with the crowdsourcing task loss ratio smaller than the loss threshold as the target task;
according to the first path and the route information of each target task, obtaining the route coincidence rate of each target task; the route coincidence rate represents the coincidence degree of the first path and the route information on direction and distance;
the step of obtaining the route coincidence rate of each target task according to the first path and the route information of each target task includes:
respectively obtaining a third distance of each target task according to the first path and the position of each target task, wherein the third distance is the shortest distance between the position of the target task and the first path; respectively obtaining direction information of each target task according to the all-time path and the first path of each target task, wherein the direction information represents the direction relationship between the all-time path and the first path of each target task; the path-all-time characterizes a travel route when the target task is completed individually; distributing weights to the direction information and the third distance and calculating to obtain the route coincidence rate of each target task;
obtaining an expected income increase value of each target task according to the route information and the route coincidence rate of each target task; the expected revenue growth value characterizes a relative magnitude of revenue obtained after the target task is completed by the crowdsourcing worker;
assigning the target task with the largest expected revenue growth value to the crowdsourcing worker.
2. The method of claim 1, wherein after said obtaining a route coincidence rate for each of said target missions and before said obtaining an expected revenue growth value for each of said target missions based on said route information for each of said target missions and said route coincidence rate, said method further comprises:
determining at least one target task meeting a preset route coincidence rate range from the plurality of target tasks as a candidate task according to the size of the route coincidence rate;
wherein the obtaining an expected revenue increase value of each target task according to the route information and the route coincidence rate of each target task comprises:
obtaining an expected income increase value of each candidate task according to the route information and the route coincidence rate of each candidate task;
wherein said assigning the target task with the largest expected revenue growth value to the crowdsourcing workers comprises:
assigning the candidate task with the largest expected revenue growth value to the crowdsourcing worker.
3. The method according to any one of claims 1-2, wherein before the step of screening out a plurality of tasks to be assigned meeting a preset distance requirement as target tasks according to the first path of crowdsourcing workers who have carried the tasks and the positions of the plurality of tasks to be assigned, the method further comprises:
acquiring a first time difference corresponding to a published task and a second time difference generated by the crowd-sourcing worker moving from a current position to a position of the published task in a shortest path;
and determining the published task with the first time difference larger than the second time difference as the task to be distributed.
4. The method according to any one of claims 1-2, wherein before the step of screening out a plurality of tasks to be assigned meeting a preset distance requirement as target tasks according to the first path of crowdsourcing workers who have carried the tasks and the positions of the plurality of tasks to be assigned, the method further comprises:
respectively defining a target area range for each published task of unallocated workers;
according to the probability that the target area range is visited by random workers of each unassigned task, obtaining the position entropy of each issued task, wherein the position entropy represents the disorder of the visited tasks of the issued task by the random workers of the unassigned task;
and sequentially distributing tasks for the random workers according to the position entropy of the issued tasks.
5. The method of claim 4, wherein said step of sequentially assigning tasks to said random worker comprises:
acquiring the travel expense between each random worker and the published task;
matching the issued task with the minimum position entropy and the random worker with the minimum issued task travel expense; and after the matching is successful, the mobile terminal is taken as a crowdsourcing worker with a task.
6. The method of claim 5, wherein the trip cost is computed using Manhattan distance.
7. A spatiotemporal crowdsourcing online task distribution system, the system comprising:
the task screening module is used for screening a plurality of tasks to be distributed which meet the preset distance requirement as target tasks according to a first path of crowdsourcing workers who carry the tasks and the positions of the tasks to be distributed; the first path is a path between the current position of the crowdsourcing worker and the end position of the task carried by the crowdsourcing worker, and each task to be distributed has corresponding route information; the task screening module is further specifically configured to: respectively obtaining a second path of each task to be distributed according to the first path and the positions of the tasks to be distributed; the first path length corresponds to a first distance value, the second path is a path between the current position of the crowdsourcing worker and the position of the task to be distributed, and the second path length corresponds to a second distance value; respectively obtaining the crowdsourcing task loss ratio of each task to be distributed according to the ratio of the first distance value to the second distance value corresponding to each task to be distributed; respectively comparing the crowdsourcing task loss ratio of each task to be allocated with a preset loss threshold, and taking the task to be allocated with the crowdsourcing task loss ratio smaller than the loss threshold as the target task;
the route calculation module is used for obtaining the route coincidence rate of each target task according to the first path and the route information of each target task; the route coincidence rate represents the coincidence degree of the first path and the route information on direction and distance; the route calculation module is further specifically configured to: respectively obtaining a third distance of each target task according to the first path and the position of each target task, wherein the third distance is the shortest distance between the position of the target task and the first path; respectively obtaining direction information of each target task according to the all-time path and the first path of each target task, wherein the direction information represents the direction relationship between the all-time path and the first path of each target task; the path-all-time characterizes a travel route when the target task is completed individually; distributing weights to the direction information and the third distance and calculating to obtain the route coincidence rate of each target task;
the profit calculation module is used for obtaining an expected profit growth value of each target task according to the route information of each target task and the route coincidence rate; the expected revenue growth value characterizes a relative magnitude of revenue obtained after the target task is completed by the crowdsourcing worker;
an allocation module to allocate the target task with the largest expected revenue growth value to the crowdsourcing worker.
CN201811032833.0A 2018-09-05 2018-09-05 Space-time crowdsourcing online task allocation method and system Expired - Fee Related CN109325671B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811032833.0A CN109325671B (en) 2018-09-05 2018-09-05 Space-time crowdsourcing online task allocation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811032833.0A CN109325671B (en) 2018-09-05 2018-09-05 Space-time crowdsourcing online task allocation method and system

Publications (2)

Publication Number Publication Date
CN109325671A CN109325671A (en) 2019-02-12
CN109325671B true CN109325671B (en) 2020-05-12

Family

ID=65264316

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811032833.0A Expired - Fee Related CN109325671B (en) 2018-09-05 2018-09-05 Space-time crowdsourcing online task allocation method and system

Country Status (1)

Country Link
CN (1) CN109325671B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110401718A (en) * 2019-07-29 2019-11-01 腾讯科技（深圳）有限公司 Method for allocating tasks, device, server and storage medium based on space crowdsourcing
CN111260281A (en) * 2020-01-13 2020-06-09 拉扎斯网络科技（上海）有限公司 Task processing method and device, electronic equipment and computer readable storage medium
CN113537672A (en) * 2020-04-15 2021-10-22 北京旷视机器人技术有限公司 Task allocation method, task allocation device, medium, and electronic device
CN111667137B (en) * 2020-04-19 2022-07-05 北京理工大学 Random cross online matching method in space-time crowdsourcing platform
CN111680860B (en) * 2020-04-19 2022-09-02 北京理工大学 Deterministic cross online matching method in space-time crowdsourcing platform
CN112348487A (en) * 2020-11-30 2021-02-09 深圳淘力网络科技有限公司 Intelligent outsourcing system based on block chain and using method thereof
CN112884319B (en) * 2021-02-10 2023-11-03 腾讯大地通途（北京）科技有限公司 Task allocation method and device, computer equipment and storage medium
CN113128897B (en) * 2021-04-30 2024-04-05 平安国际融资租赁有限公司 Crowd-sourced task resource configuration method and device, electronic equipment and storage medium
CN115879722B (en) * 2022-12-14 2023-09-22 南京捷崎信息科技有限公司 Space crowdsourcing task allocation method and system

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3279851A4 (en) * 2015-03-31 2018-04-11 Mitsubishi Heavy Industries, Ltd. Route planning system, route planning method, article-arrangement planning system, article-arrangement planning method, decision-making support system, computer program, and storage medium
CN105719010A (en) * 2015-07-24 2016-06-29 北京小度信息科技有限公司 Method and device for processing distribution tasks
CN108182556B (en) * 2016-12-08 2021-07-20 北京京东乾石科技有限公司 Distribution method and device for unmanned vehicle and unmanned vehicle
CN108241930A (en) * 2017-12-29 2018-07-03 儒安科技有限公司 A kind of method for allocating tasks of mobile crowdsourcing platform
CN108038740A (en) * 2017-12-29 2018-05-15 西南大学 The crowdsourcing platform task price and distribution method of time-sensitive

Also Published As

Publication number Publication date
CN109325671A (en) 2019-02-12

Similar Documents

Publication Publication Date Title
CN109325671B (en) Space-time crowdsourcing online task allocation method and system
US11276028B2 (en) System and method for dynamic pairing function optimization
JP6707125B2 (en) System and method for assigning shareable orders
US20200118071A1 (en) Delivery prediction generation system
US20160353235A1 (en) Location-based order recommendations
US10181111B1 (en) Electronic device communications for item handoffs
US20190370922A1 (en) Price-aware real-time auction-based ride-sharing system
US11676038B2 (en) Systems and methods for multi-objective optimizations with objective space mapping
KR20180013843A (en) Order allocation system and method
US11188932B2 (en) Method, apparatus, and computer program product for providing mobile location based sales lead identification
CN107657364A (en) A kind of overloading AGV tasks towards tobacco plant material transportation distribute forming method
US20110166958A1 (en) Conducting route commerce from a central clearinghouse
CN107317872B (en) Scheduling method of multi-type tasks in space crowdsourcing
CN109934372B (en) Path planning method, device and equipment
JP2018206225A (en) Distribution device, distribution method, distribution program, and model
AU2018217973A1 (en) Dynamic selection of geo-based service options in a network system
US20200226506A1 (en) Methods and systems for automated salesbeat optimization
Seo et al. Rebalancing docked bicycle sharing system with approximate dynamic programming and reinforcement learning
US20210019788A1 (en) Location-based mobile promotion campaign
CN113379360B (en) Commodity secondary transaction method, commodity secondary transaction device, electronic equipment and computer readable medium
WO2020244081A1 (en) Constrained spatiotemporal contextual bandits for real-time ride-hailing recommendation
US20240220893A1 (en) Work management platform
US20240220894A1 (en) Work management platform
Shen et al. An Auction‐Based Multiagent Simulation for the Matching Problem in Dynamic Vehicle Routing Problem with Occasional Drivers
AU2019204134A1 (en) Future order throttling

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20200512